This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: atomic_thread_fence() semantics
- From: Jonathan Wakely <jwakely dot gcc at gmail dot com>
- To: Mattias Rönnblom <hofors at lysator dot liu dot se>
- Cc: "gcc at gcc dot gnu dot org" <gcc at gcc dot gnu dot org>
- Date: Thu, 19 Oct 2017 13:10:17 +0100
- Subject: Re: atomic_thread_fence() semantics
- Authentication-results: sourceware.org; auth=none
- References: <351d54cc-4da1-dd20-aace-17c5b6244e1a@lysator.liu.se>
On 19 October 2017 at 12:58, Mattias Rönnblom wrote:
> Hi.
>
> I have this code:
>
> #include <stdatomic.h>
>
> int ready;
> int message;
>
> void send_x4711(int m) {
> message = m*4711;
> atomic_thread_fence(memory_order_release);
> ready = 1;
> }
>
> When I compile it with GCC 7.2 -O3 -std=c11 on x86_64 it produces the
> following code:
>
> send_x4711:
> .LFB0:
> .LVL0:
> imul edi, edi, 4711
> .LVL1:
> mov DWORD PTR ready[rip], 1
> mov DWORD PTR message[rip], edi
> ret
>
> I expected the store to 'message' and 'ready' to be in program order.
>
> Did I misunderstand the semantics of
> atomic_thread_fence+memory_order_release?
There are no atomic operations on atomic objects here, so the fence
doesn't synchronize with anything.